Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks

Karen Tovar; Marvin Coto-Jimenez; Mauricio Gutierrez; Ignacio Borge

doi:10.1109/bip60195.2023.10379240

Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks

Karen Tovar, Marvin Coto-Jimenez, Mauricio Gutierrez, Ignacio Borge

Department of Chemistry

University of Costa Rica

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Carbides, as exemplified by Mo2C, have various valuable properties that affect various industries. Understanding the influence of carbon vacancy patterns on these properties is an essential yet challenging task. This work presents a two-stage approach. First, novel numerical descriptors linked to molecular structure are predicted using Neural Networks. Subsequently, using these descriptors alone, carbide vacancy energy is accurately forecasted through Neural Networks and an Attention mechanism. The correlation unveiled hints at a numerical relationship between these descriptors and energy, opening avenues for interpreting their significance. This research contributes to computational materials science, offering insights into carbide intricacies and inspiring innovative applications.

Original language	English
Title of host publication	5th IEEE International Conference on BioInspired Processing, BIP 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350330052
DOIs	https://doi.org/10.1109/bip60195.2023.10379240
State	Published - 2023
Event	5th IEEE International Conference on BioInspired Processing, BIP 2023 - San Carlos, Alajuela, Costa Rica Duration: 28 Nov 2023 → 30 Nov 2023

Publication series

Name	5th IEEE International Conference on BioInspired Processing, BIP 2023

Conference

Conference	5th IEEE International Conference on BioInspired Processing, BIP 2023
Country/Territory	Costa Rica
City	San Carlos, Alajuela
Period	28/11/23 → 30/11/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Convolutional Neural Networks
Descriptor Prediction
Graph Neural Networks (GNN)
Machine Learning
Molybdenum Carbide
Vacancy Energy

Access to Document

10.1109/bip60195.2023.10379240

Cite this

Tovar, K., Coto-Jimenez, M., Gutierrez, M., & Borge, I. (2023). Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks. In 5th IEEE International Conference on BioInspired Processing, BIP 2023 (5th IEEE International Conference on BioInspired Processing, BIP 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/bip60195.2023.10379240

Tovar, Karen ; Coto-Jimenez, Marvin ; Gutierrez, Mauricio et al. / Unlocking Carbide Vacancy Energy in Molybdenum Carbide : Predictive Insights from Numerical Descriptors and Neural Networks. 5th IEEE International Conference on BioInspired Processing, BIP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (5th IEEE International Conference on BioInspired Processing, BIP 2023).

@inproceedings{e33424d701df43fd976ad823987b8338,

title = "Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks",

abstract = "Carbides, as exemplified by Mo2C, have various valuable properties that affect various industries. Understanding the influence of carbon vacancy patterns on these properties is an essential yet challenging task. This work presents a two-stage approach. First, novel numerical descriptors linked to molecular structure are predicted using Neural Networks. Subsequently, using these descriptors alone, carbide vacancy energy is accurately forecasted through Neural Networks and an Attention mechanism. The correlation unveiled hints at a numerical relationship between these descriptors and energy, opening avenues for interpreting their significance. This research contributes to computational materials science, offering insights into carbide intricacies and inspiring innovative applications.",

keywords = "Convolutional Neural Networks, Descriptor Prediction, Graph Neural Networks (GNN), Machine Learning, Molybdenum Carbide, Vacancy Energy",

author = "Karen Tovar and Marvin Coto-Jimenez and Mauricio Gutierrez and Ignacio Borge",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 5th IEEE International Conference on BioInspired Processing, BIP 2023 ; Conference date: 28-11-2023 Through 30-11-2023",

year = "2023",

doi = "10.1109/bip60195.2023.10379240",

language = "אנגלית",

series = "5th IEEE International Conference on BioInspired Processing, BIP 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "5th IEEE International Conference on BioInspired Processing, BIP 2023",

address = "ארצות הברית",

}

Tovar, K, Coto-Jimenez, M, Gutierrez, M & Borge, I 2023, Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks. in 5th IEEE International Conference on BioInspired Processing, BIP 2023. 5th IEEE International Conference on BioInspired Processing, BIP 2023, Institute of Electrical and Electronics Engineers Inc., 5th IEEE International Conference on BioInspired Processing, BIP 2023, San Carlos, Alajuela, Costa Rica, 28/11/23. https://doi.org/10.1109/bip60195.2023.10379240

Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks. / Tovar, Karen; Coto-Jimenez, Marvin; Gutierrez, Mauricio et al.
5th IEEE International Conference on BioInspired Processing, BIP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (5th IEEE International Conference on BioInspired Processing, BIP 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Unlocking Carbide Vacancy Energy in Molybdenum Carbide

T2 - 5th IEEE International Conference on BioInspired Processing, BIP 2023

AU - Tovar, Karen

AU - Coto-Jimenez, Marvin

AU - Gutierrez, Mauricio

AU - Borge, Ignacio

PY - 2023

Y1 - 2023

N2 - Carbides, as exemplified by Mo2C, have various valuable properties that affect various industries. Understanding the influence of carbon vacancy patterns on these properties is an essential yet challenging task. This work presents a two-stage approach. First, novel numerical descriptors linked to molecular structure are predicted using Neural Networks. Subsequently, using these descriptors alone, carbide vacancy energy is accurately forecasted through Neural Networks and an Attention mechanism. The correlation unveiled hints at a numerical relationship between these descriptors and energy, opening avenues for interpreting their significance. This research contributes to computational materials science, offering insights into carbide intricacies and inspiring innovative applications.

AB - Carbides, as exemplified by Mo2C, have various valuable properties that affect various industries. Understanding the influence of carbon vacancy patterns on these properties is an essential yet challenging task. This work presents a two-stage approach. First, novel numerical descriptors linked to molecular structure are predicted using Neural Networks. Subsequently, using these descriptors alone, carbide vacancy energy is accurately forecasted through Neural Networks and an Attention mechanism. The correlation unveiled hints at a numerical relationship between these descriptors and energy, opening avenues for interpreting their significance. This research contributes to computational materials science, offering insights into carbide intricacies and inspiring innovative applications.

KW - Convolutional Neural Networks

KW - Descriptor Prediction

KW - Graph Neural Networks (GNN)

KW - Machine Learning

KW - Molybdenum Carbide

KW - Vacancy Energy

UR - http://www.scopus.com/inward/record.url?scp=85184353161&partnerID=8YFLogxK

U2 - 10.1109/bip60195.2023.10379240

DO - 10.1109/bip60195.2023.10379240

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85184353161

T3 - 5th IEEE International Conference on BioInspired Processing, BIP 2023

BT - 5th IEEE International Conference on BioInspired Processing, BIP 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 28 November 2023 through 30 November 2023

ER -

Tovar K, Coto-Jimenez M, Gutierrez M, Borge I. Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks. In 5th IEEE International Conference on BioInspired Processing, BIP 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (5th IEEE International Conference on BioInspired Processing, BIP 2023). doi: 10.1109/bip60195.2023.10379240

Unlocking Carbide Vacancy Energy in Molybdenum Carbide: Predictive Insights from Numerical Descriptors and Neural Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this